Merge tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fs hole punching vs cache filling race fixes from Jan Kara:
 "Fix races leading to possible data corruption or stale data exposure
  in multiple filesystems when hole punching races with operations such
  as readahead.

  This is the series I was sending for the last merge window but with
  your objection fixed - now filemap_fault() has been modified to take
  invalidate_lock only when we need to create new page in the page cache
  and / or bring it uptodate"

* tag 'hole_punch_for_v5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  filesystems/locking: fix Malformed table warning
  cifs: Fix race between hole punch and page fault
  ceph: Fix race between hole punch and page fault
  fuse: Convert to using invalidate_lock
  f2fs: Convert to using invalidate_lock
  zonefs: Convert to using invalidate_lock
  xfs: Convert double locking of MMAPLOCK to use VFS helpers
  xfs: Convert to use invalidate_lock
  xfs: Refactor xfs_isilocked()
  ext2: Convert to using invalidate_lock
  ext4: Convert to use mapping->invalidate_lock
  mm: Add functions to lock invalidate_lock for two mappings
  mm: Protect operations adding pages to page cache with invalidate_lock
  documentation: Sync file_operations members with reality
  mm: Fix comments mentioning i_mutex

1 files changed, 39 insertions, 0 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index bea8ec5c726c..eb668b58f7f6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -436,6 +436,10 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
  * struct address_space - Contents of a cacheable, mappable object.
  * @host: Owner, either the inode or the block_device.
  * @i_pages: Cached pages.
+ * @invalidate_lock: Guards coherency between page cache contents and
+ *   file offset->disk block mappings in the filesystem during invalidates.
+ *   It is also used to block modification of page cache contents through
+ *   memory mappings.
  * @gfp_mask: Memory allocation flags to use for allocating pages.
  * @i_mmap_writable: Number of VM_SHARED mappings.
  * @nr_thps: Number of THPs in the pagecache (non-shmem only).
@@ -453,6 +457,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
 struct address_space {
 	struct inode		*host;
 	struct xarray		i_pages;
+	struct rw_semaphore	invalidate_lock;
 	gfp_t			gfp_mask;
 	atomic_t		i_mmap_writable;
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
@@ -814,9 +819,42 @@ static inline void inode_lock_shared_nested(struct inode *inode, unsigned subcla
 	down_read_nested(&inode->i_rwsem, subclass);
 }
 
+static inline void filemap_invalidate_lock(struct address_space *mapping)
+{
+	down_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock(struct address_space *mapping)
+{
+	up_write(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
+{
+	down_read(&mapping->invalidate_lock);
+}
+
+static inline int filemap_invalidate_trylock_shared(
+					struct address_space *mapping)
+{
+	return down_read_trylock(&mapping->invalidate_lock);
+}
+
+static inline void filemap_invalidate_unlock_shared(
+					struct address_space *mapping)
+{
+	up_read(&mapping->invalidate_lock);
+}
+
 void lock_two_nondirectories(struct inode *, struct inode*);
 void unlock_two_nondirectories(struct inode *, struct inode*);
 
+void filemap_invalidate_lock_two(struct address_space *mapping1,
+				 struct address_space *mapping2);
+void filemap_invalidate_unlock_two(struct address_space *mapping1,
+				   struct address_space *mapping2);
+
+
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
@@ -2490,6 +2528,7 @@ struct file_system_type {
 
 	struct lock_class_key i_lock_key;
 	struct lock_class_key i_mutex_key;
+	struct lock_class_key invalidate_lock_key;
 	struct lock_class_key i_mutex_dir_key;
 };